Qwen3.8 27B
qwen/qwen3.8-27b
Compare with Qwen3.8 2.4T A95B, Qwen-Plus, Qwen3.8 Max
CompareQwen3.8 27B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.75% | 1.45s | 6.78s | 48 tps | 1.0M | $0.550 / $3.30 |
Venicevenice/fp8fp8 | Healthy | 100% | 98.35% | 885ms | 4.25s | 116 tps | 262K | $0.450 / $3.20 |
AkashMLakashml/bf16bf16 | Healthy | 99.70% | 99.17% | 1.49s | 26.2s | 38 tps | 262K | $0.450 / $3.20 |
Chuteschutes/fp8fp8 | Healthy | 99.24% | 98.87% | 1.61s | 40.9s | 22 tps | 262K | $0.400 / $3.00 |
Rekareka/fp8fp8 | Healthy | 98.39% | 99.03% | 1.40s | 14.1s | 53 tps | 262K | $0.450 / $3.20 |
Io Netio-net/fp8fp8 | No data | — | 98.46% | 2.63s | 13.6s | 30 tps | 66K | $0.480 / $3.40 |
- Alibaba100%Healthy24h 99.75%
- p50
- 1.45s
- p99
- 6.78s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $0.550 / $3.30
alibaba - Venice100%Healthy24h 98.35%
- p50
- 885ms
- p99
- 4.25s
- Throughput
- 116 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
venice/fp8fp8 - AkashML99.70%Healthy24h 99.17%
- p50
- 1.49s
- p99
- 26.2s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
akashml/bf16bf16 - Chutes99.24%Healthy24h 98.87%
- p50
- 1.61s
- p99
- 40.9s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.400 / $3.00
chutes/fp8fp8 - Reka98.39%Healthy24h 99.03%
- p50
- 1.40s
- p99
- 14.1s
- Throughput
- 53 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
reka/fp8fp8 - Io Net—No data24h 98.46%
- p50
- 2.63s
- p99
- 13.6s
- Throughput
- 30 tps
- Context
- 66K
- $/Mtok
- $0.480 / $3.40
io-net/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.